Transcribe audio using huggingface

[neuralsignal]

Background
Addition of a audio transcriber command that uses the huggingface inference API to call an audio to text model.

Changes
Added a new python file called audio_text.py that contains the read_audio function, which call the huggingface API.
Made changes to prompt.py, the env template, config.py, and app.py to include the read_audio function and make it functional.

Documentation
The changes are implemented as just in code comments.

Test Plan
I tested the changes by added various audio samples to the working directory. Then I asked the agent to transcribe the audio samples and compare the transcribed stories to each other.

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes